resemble-ai/resemble-enhance ? reverse-engineered prompt
Reverse engineered prompt
Build me a Python app that cleans up speech audio files with AI. I want to be able to drop in a folder of noisy wav files and get an output folder with the improved versions, with a mode for full enhancement and another mode for denoising only.
It should also have a simple local web demo where I can upload audio, listen to the before and after, and download the result. If it makes sense, include a basic command line tool for batch processing too, so I can run it from the terminal.
Please keep it focused on speech, not music, and make the results sound clearer and more natural by removing background noise and fixing audio quality. If you need current docs or model details, look them up online first. Also include a clean way to train or fine tune the models from prepared speech, noise, and room response data, but keep the default setup easy to run.
Are you gonna build this?
make sure you review the code using coderabbit